JSAI Technical Report, Type 2 SIG
Online ISSN : 2436-5556
Event Prediction in Event-Centric Knowledge Graphs Using LLM
Takanori UGAI
Author information
RESEARCH REPORT / TECHNICAL REPORT FREE ACCESS

2023 Volume 2023 Issue SWO-061 Pages 08-

Details
Abstract

The dataset provided by the Knowledge Graph Reasoning Challenge for Social Issues (KGRC4SI) is an event-centric knowledge graph representation of avatar behavior in a virtual space. Therefore, it contains information on the entire virtual space, including parts of the virtual space that are hidden in the video. However, some information cannot be obtained by any means, for example, when sensor data from the real world is collected. In this paper, we report a method for predicting the hidden parts using LLM and the results of experiments using this method, using the KGRC4SI dataset as complete data for training.

Content from these authors
© 2023 Authors
Previous article Next article
feedback
Top